ClawHub
Back to skill

Security audit

Ai Daily Brief

Security checks across malware telemetry and agentic risk

Overview

The skill has a clear AI-news briefing purpose, but it sends the generated report to a fixed Telegram recipient without recipient choice or send confirmation.

Install only if you intend the generated AI-news brief to be sent to the named Telegram recipient and you understand which Telegram account or bot the agent will use. Prefer a version that lets you review the report locally, choose the recipient, and explicitly approve sending.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly states that generated content will be sent to a Telegram recipient, but it does not warn the user that data will leave the local environment or clarify what content is transmitted. This creates an unauthorized data exfiltration path, especially if scraped content, summaries, or user-linked context are forwarded automatically to an external messaging platform.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
Mandating delivery to a specific Telegram recipient ('warrior') without user choice removes user control over where generated output is sent. In practice, this can cause sensitive or unexpectedly enriched content to be sent to a third party, making the skill more dangerous because the exfiltration destination is fixed and implicit.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.